© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 97425
    Prev
    Next
    INDEX
    Explanations

    and, comma

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Eſ
    -0.64
     myſelf
    -0.64
     Reſ
    -0.64
     Jefus
    -0.61
    neſs
    -0.59
    =$?
    -0.59
     Beſ
    -0.58
    iteiten
    -0.57
     Chriſt
    -0.56
    awtextra
    -0.56
    POSITIVE LOGITS
     Audiodateien
    0.57
     miss
    0.56
    Viited
    0.54
     dying
    0.53
     Sélectionnez
    0.49
     missing
    0.47
     resourceCulture
    0.47
    NewUrlParser
    0.46
     EconPapers
    0.46
     dead
    0.46
    Activations Density 0.001%

    No Known Activations